NEWMEN
← back to all models

Qwen: Qwen3 32B

qwen/qwen3-32b

Alibaba (Qwen)open-weight131K context7 providersIntelligence 70.9

Cheapest provider

$0.08 / 1M

DeepInfra

Fastest provider (p95)

No throughput data yet — populated as traffic accumulates

Intelligence (composite)

70.9

MMLU-Pro · HumanEval · math · GPQA

Per-provider performance

Latency / throughput / uptime measured across providers over the last 30 minutes of live traffic. Atlas’s router weighs these per call (with the eval-gate signal) when picking a variant for Standard and Batch tiers.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
DeepInfraq8· fp8$0.0800$0.280099.94%
AtlasCloudq8· fp8$0.1000$1.2000100.00%
Nebiusq8· fp8$0.1000$0.3000100.00%
Novitaq8· fp8$0.1000$0.450087.17%
Alibabaundisclosed$0.1040$0.4160100.00%
SiliconFlowq8· fp8$0.1400$0.570083.85%
Groqundisclosed$0.2900$0.5900100.00%

“—” means live telemetry hasn’t accumulated enough recent traffic for that endpoint. “undisclosed” means the provider serves the model but doesn’t expose the quantization label (typically running fp8 / int8 internally).

Intelligence breakdown

Composite score is a weighted average of public benchmarks (30% MMLU-Pro, 25% code pass@1, 25% math, 20% GPQA). Numbers come from model cards and the Artificial Analysis intelligence harness; missing components are renormalised over what’s present.

MMLU-Pro

broad reasoning

Code

pass@1 (HumanEval / LiveCodeBench)

AIME 2025

72.9

math accuracy

GPQA Diamond

68.4

hard reasoning

Source: Qwen3-32B (GPQA-Diamond 68.4, AIME25 72.9); DeepSeek-R1-0528 model card comparison table

How Atlas routes Qwen: Qwen3 32B

  • Realtime tier — direct passthrough at the upstream’s native precision. Best for hard latency / quality guarantees.
  • Standard tier — Atlas picks the cheapest provider variant whose quantization has stayed green on your operation’s eval gates. For Qwen: Qwen3 32B that’s currently DeepInfra at $0.08/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.